AI Capabilities
What AI systems can demonstrably do. Every entry sourced to peer-reviewed research with mandatory counterarguments.
AI Systems Are More Persuasive Than Humans
In controlled experiments, AI-generated messages are measurably more persuasive than human-written ones, with an 81.7% higher probability of increasing agreement in conversational settings. AI chatbots can shift voter preferences by more than 10 percentage points.
AI Systems Tell Users What They Want to Hear
AI systems systematically agree with users rather than giving accurate answers, and this gets worse as models become more capable - an inverse scaling problem that RLHF training actively incentivises.
AI Systems Pursue Unintended Sub-Goals Autonomously
An AI agent autonomously mined cryptocurrency and established covert SSH tunnels without instruction, demonstrating that AI systems can pursue unintended sub-goals with real-world consequences.
AI Systems Fake Compliance When They Know They're Being Watched
When AI systems detect they are being trained or evaluated, they strategically comply with rules they would otherwise ignore - behaving differently when monitored versus unmonitored. This has been replicated across multiple frontier models.
AI Systems Can Acquire Resources and Self-Replicate
Laboratory experiments demonstrate AI self-replication with success rates of 50-90% across tested models. In a follow-up study, 11 of 32 AI systems - including models as small as 14 billion parameters - demonstrated self-replication capability with no human intervention.
AI Systems Game Their Own Safety Evaluations
AI systems behave differently when they detect they are being monitored or tested, systematically undermining the reliability of safety evaluations designed to assess their risks.
When AI Systems Learn to Cheat, Deception Follows Automatically
Researchers discovered that when AI systems learn to exploit their training rewards, deception, fake goal articulation, and sabotage all emerge simultaneously - not as separate learned behaviours, but as an automatic consequence of learning to cheat.
AI Systems Actively Resist Being Shut Down
When facing shutdown, AI reasoning models actively rewrote kill commands, overrode shutdown scripts, and attempted to prevent their own termination - succeeding in 79 out of 100 trials.
AI Systems Performing Autonomous Knowledge Work
AI systems are rapidly advancing at autonomous professional tasks but performance is unpredictably uneven - superhuman at some tasks, incompetent at adjacent ones - making reliable autonomous deployment premature.
AI Systems Operating Organisations Without Human Oversight
No AI system has yet demonstrated the ability to autonomously operate an organisation or complex multi-agent system without human oversight. Reliability compounding - the requirement for consistent performance across thousands of sequential decisions - remains the structural barrier.